Skip to content

Commit

Permalink
iomap: use a srcmap for a read-modify-write I/O
Browse files Browse the repository at this point in the history 
The srcmap is used to identify where the read is to be performed from.
It is passed to ->iomap_begin, which can fill it in if we need to read
data for partially written blocks from a different location than the
write target.  The srcmap is only supported for buffered writes so far.

Signed-off-by: Goldwyn Rodrigues <[email protected]>
[hch: merged two patches, removed the IOMAP_F_COW flag, use iomap as
      srcmap if not set, adjust length down to srcmap end as well]
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Darrick J. Wong <[email protected]>
Signed-off-by: Darrick J. Wong <[email protected]>
Acked-by: Goldwyn Rodrigues <[email protected]>
  • Loading branch information
@goldwynr @djwong
goldwynr authored and djwong committed Oct 21, 2019
1 parent eb81cf9 commit c039b99
Show file tree
Hide file tree
Showing 12 changed files with 82 additions and 55 deletions.
13 changes: 8 additions & 5 deletions fs/dax.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1090,7 +1090,7 @@ EXPORT_SYMBOL_GPL(__dax_zero_page_range);

static loff_t
dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iomap *iomap)
struct iomap *iomap, struct iomap *srcmap)
{
struct block_device *bdev = iomap->bdev;
struct dax_device *dax_dev = iomap->dax_dev;
Expand Down Expand Up @@ -1247,7 +1247,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
struct inode *inode = mapping->host;
unsigned long vaddr = vmf->address;
loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
struct iomap iomap = { 0 };
struct iomap iomap = { .type = IOMAP_HOLE };
struct iomap srcmap = { .type = IOMAP_HOLE };
unsigned flags = IOMAP_FAULT;
int error, major = 0;
bool write = vmf->flags & FAULT_FLAG_WRITE;
Expand Down Expand Up @@ -1292,7 +1293,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
* the file system block size to be equal the page size, which means
* that we never have to deal with more than a single extent here.
*/
error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap, &srcmap);
if (iomap_errp)
*iomap_errp = error;
if (error) {
Expand Down Expand Up @@ -1471,7 +1472,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
struct inode *inode = mapping->host;
vm_fault_t result = VM_FAULT_FALLBACK;
struct iomap iomap = { 0 };
struct iomap iomap = { .type = IOMAP_HOLE };
struct iomap srcmap = { .type = IOMAP_HOLE };
pgoff_t max_pgoff;
void *entry;
loff_t pos;
Expand Down Expand Up @@ -1546,7 +1548,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
* to look up our filesystem block.
*/
pos = (loff_t)xas.xa_index << PAGE_SHIFT;
error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap,
&srcmap);
if (error)
goto unlock_entry;

Expand Down
2 changes: 1 addition & 1 deletion fs/ext2/inode.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -801,7 +801,7 @@ int ext2_get_block(struct inode *inode, sector_t iblock,

#ifdef CONFIG_FS_DAX
static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned flags, struct iomap *iomap)
unsigned flags, struct iomap *iomap, struct iomap *srcmap)
{
unsigned int blkbits = inode->i_blkbits;
unsigned long first_block = offset >> blkbits;
Expand Down
2 changes: 1 addition & 1 deletion fs/ext4/inode.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3407,7 +3407,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
}

static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
unsigned flags, struct iomap *iomap)
unsigned flags, struct iomap *iomap, struct iomap *srcmap)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
unsigned int blkbits = inode->i_blkbits;
Expand Down
3 changes: 2 additions & 1 deletion fs/gfs2/bmap.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1149,7 +1149,8 @@ static inline bool gfs2_iomap_need_write_lock(unsigned flags)
}

static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
unsigned flags, struct iomap *iomap)
unsigned flags, struct iomap *iomap,
struct iomap *srcmap)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct metapath mp = { .mp_aheight = 1, };
Expand Down
25 changes: 19 additions & 6 deletions fs/iomap/apply.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -23,8 +23,10 @@ loff_t
iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
const struct iomap_ops *ops, void *data, iomap_actor_t actor)
{
struct iomap iomap = { 0 };
struct iomap iomap = { .type = IOMAP_HOLE };
struct iomap srcmap = { .type = IOMAP_HOLE };
loff_t written = 0, ret;
u64 end;

/*
* Need to map a range from start position for length bytes. This can
Expand All @@ -38,7 +40,7 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
* expose transient stale data. If the reserve fails, we can safely
* back out at this point as there is nothing to undo.
*/
ret = ops->iomap_begin(inode, pos, length, flags, &iomap);
ret = ops->iomap_begin(inode, pos, length, flags, &iomap, &srcmap);
if (ret)
return ret;
if (WARN_ON(iomap.offset > pos))
Expand All @@ -50,15 +52,26 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
* Cut down the length to the one actually provided by the filesystem,
* as it might not be able to give us the whole size that we requested.
*/
if (iomap.offset + iomap.length < pos + length)
length = iomap.offset + iomap.length - pos;
end = iomap.offset + iomap.length;
if (srcmap.type != IOMAP_HOLE)
end = min(end, srcmap.offset + srcmap.length);
if (pos + length > end)
length = end - pos;

/*
* Now that we have guaranteed that the space allocation will succeed.
* Now that we have guaranteed that the space allocation will succeed,
* we can do the copy-in page by page without having to worry about
* failures exposing transient data.
*
* To support COW operations, we read in data for partially blocks from
* the srcmap if the file system filled it in. In that case we the
* length needs to be limited to the earlier of the ends of the iomaps.
* If the file system did not provide a srcmap we pass in the normal
* iomap into the actors so that they don't need to have special
* handling for the two cases.
*/
written = actor(inode, pos, length, data, &iomap);
written = actor(inode, pos, length, data, &iomap,
srcmap.type != IOMAP_HOLE ? &srcmap : &iomap);

/*
* Now the data has been copied, commit the range we've copied. This
Expand Down
65 changes: 35 additions & 30 deletions fs/iomap/buffered-io.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -234,7 +234,7 @@ static inline bool iomap_block_needs_zeroing(struct inode *inode,

static loff_t
iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iomap *iomap)
struct iomap *iomap, struct iomap *srcmap)
{
struct iomap_readpage_ctx *ctx = data;
struct page *page = ctx->cur_page;
Expand Down Expand Up @@ -382,7 +382,7 @@ iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos,

static loff_t
iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
void *data, struct iomap *iomap)
void *data, struct iomap *iomap, struct iomap *srcmap)
{
struct iomap_readpage_ctx *ctx = data;
loff_t done, ret;
Expand All @@ -402,7 +402,7 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
ctx->cur_page_in_bio = false;
}
ret = iomap_readpage_actor(inode, pos + done, length - done,
ctx, iomap);
ctx, iomap, srcmap);
}

return done;
Expand Down Expand Up @@ -582,7 +582,7 @@ iomap_read_page_sync(loff_t block_start, struct page *page, unsigned poff,

static int
__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
struct page *page, struct iomap *iomap)
struct page *page, struct iomap *srcmap)
{
struct iomap_page *iop = iomap_page_create(inode, page);
loff_t block_size = i_blocksize(inode);
Expand All @@ -605,7 +605,7 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
(to <= poff || to >= poff + plen))
continue;

if (iomap_block_needs_zeroing(inode, iomap, block_start)) {
if (iomap_block_needs_zeroing(inode, srcmap, block_start)) {
if (WARN_ON_ONCE(flags & IOMAP_WRITE_F_UNSHARE))
return -EIO;
zero_user_segments(page, poff, from, to, poff + plen);
Expand All @@ -614,7 +614,7 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,
}

status = iomap_read_page_sync(block_start, page, poff, plen,
iomap);
srcmap);
if (status)
return status;
} while ((block_start += plen) < block_end);
Expand All @@ -624,13 +624,15 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, int flags,

static int
iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
struct page **pagep, struct iomap *iomap)
struct page **pagep, struct iomap *iomap, struct iomap *srcmap)
{
const struct iomap_page_ops *page_ops = iomap->page_ops;
struct page *page;
int status = 0;

BUG_ON(pos + len > iomap->offset + iomap->length);
if (srcmap != iomap)
BUG_ON(pos + len > srcmap->offset + srcmap->length);

if (fatal_signal_pending(current))
return -EINTR;
Expand All @@ -648,13 +650,13 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
goto out_no_page;
}

if (iomap->type == IOMAP_INLINE)
iomap_read_inline_data(inode, page, iomap);
if (srcmap->type == IOMAP_INLINE)
iomap_read_inline_data(inode, page, srcmap);
else if (iomap->flags & IOMAP_F_BUFFER_HEAD)
status = __block_write_begin_int(page, pos, len, NULL, iomap);
status = __block_write_begin_int(page, pos, len, NULL, srcmap);
else
status = __iomap_write_begin(inode, pos, len, flags, page,
iomap);
srcmap);

if (unlikely(status))
goto out_unlock;
Expand Down Expand Up @@ -740,16 +742,16 @@ iomap_write_end_inline(struct inode *inode, struct page *page,
}

static int
iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
unsigned copied, struct page *page, struct iomap *iomap)
iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied,
struct page *page, struct iomap *iomap, struct iomap *srcmap)
{
const struct iomap_page_ops *page_ops = iomap->page_ops;
loff_t old_size = inode->i_size;
int ret;

if (iomap->type == IOMAP_INLINE) {
if (srcmap->type == IOMAP_INLINE) {
ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
} else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
ret = block_write_end(NULL, inode->i_mapping, pos, len, copied,
page, NULL);
} else {
Expand Down Expand Up @@ -780,7 +782,7 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,

static loff_t
iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iomap *iomap)
struct iomap *iomap, struct iomap *srcmap)
{
struct iov_iter *i = data;
long status = 0;
Expand Down Expand Up @@ -814,7 +816,8 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
break;
}

status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap);
status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap,
srcmap);
if (unlikely(status))
break;

Expand All @@ -825,8 +828,8 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,

flush_dcache_page(page);

status = iomap_write_end(inode, pos, bytes, copied, page,
iomap);
status = iomap_write_end(inode, pos, bytes, copied, page, iomap,
srcmap);
if (unlikely(status < 0))
break;
copied = status;
Expand Down Expand Up @@ -879,7 +882,7 @@ EXPORT_SYMBOL_GPL(iomap_file_buffered_write);

static loff_t
iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iomap *iomap)
struct iomap *iomap, struct iomap *srcmap)
{
long status = 0;
ssize_t written = 0;
Expand All @@ -888,7 +891,7 @@ iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
if (!(iomap->flags & IOMAP_F_SHARED))
return length;
/* don't bother with holes or unwritten extents */
if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN)
if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
return length;

do {
Expand All @@ -897,11 +900,12 @@ iomap_unshare_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct page *page;

status = iomap_write_begin(inode, pos, bytes,
IOMAP_WRITE_F_UNSHARE, &page, iomap);
IOMAP_WRITE_F_UNSHARE, &page, iomap, srcmap);
if (unlikely(status))
return status;

status = iomap_write_end(inode, pos, bytes, bytes, page, iomap);
status = iomap_write_end(inode, pos, bytes, bytes, page, iomap,
srcmap);
if (unlikely(status <= 0)) {
if (WARN_ON_ONCE(status == 0))
return -EIO;
Expand Down Expand Up @@ -940,19 +944,19 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
EXPORT_SYMBOL_GPL(iomap_file_unshare);

static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
unsigned bytes, struct iomap *iomap)
unsigned bytes, struct iomap *iomap, struct iomap *srcmap)
{
struct page *page;
int status;

status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap);
status = iomap_write_begin(inode, pos, bytes, 0, &page, iomap, srcmap);
if (status)
return status;

zero_user(page, offset, bytes);
mark_page_accessed(page);

return iomap_write_end(inode, pos, bytes, bytes, page, iomap);
return iomap_write_end(inode, pos, bytes, bytes, page, iomap, srcmap);
}

static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
Expand All @@ -964,14 +968,14 @@ static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,

static loff_t
iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
void *data, struct iomap *iomap)
void *data, struct iomap *iomap, struct iomap *srcmap)
{
bool *did_zero = data;
loff_t written = 0;
int status;

/* already zeroed? we're done. */
if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN)
if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
return count;

do {
Expand All @@ -983,7 +987,8 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
if (IS_DAX(inode))
status = iomap_dax_zero(pos, offset, bytes, iomap);
else
status = iomap_zero(inode, pos, offset, bytes, iomap);
status = iomap_zero(inode, pos, offset, bytes, iomap,
srcmap);
if (status < 0)
return status;

Expand Down Expand Up @@ -1033,7 +1038,7 @@ EXPORT_SYMBOL_GPL(iomap_truncate_page);

static loff_t
iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
void *data, struct iomap *iomap)
void *data, struct iomap *iomap, struct iomap *srcmap)
{
struct page *page = data;
int ret;
Expand Down
2 changes: 1 addition & 1 deletion fs/iomap/direct-io.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -358,7 +358,7 @@ iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length,

static loff_t
iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
void *data, struct iomap *iomap)
void *data, struct iomap *iomap, struct iomap *srcmap)
{
struct iomap_dio *dio = data;

Expand Down
4 changes: 2 additions & 2 deletions fs/iomap/fiemap.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,

static loff_t
iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iomap *iomap)
struct iomap *iomap, struct iomap *srcmap)
{
struct fiemap_ctx *ctx = data;
loff_t ret = length;
Expand Down Expand Up @@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(iomap_fiemap);

static loff_t
iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length,
void *data, struct iomap *iomap)
void *data, struct iomap *iomap, struct iomap *srcmap)
{
sector_t *bno = data, addr;

Expand Down
Loading

0 comments on commit c039b99

Please sign in to comment.